Contriever
PulseAugur coverage of Contriever — every cluster mentioning Contriever across labs, papers, and developer communities, ranked by signal.
-
New BAR method improves LLM tool use by aligning behavior, not just semantics
Researchers have developed a new method called Behavior Aligned Retrieval (BAR) to improve the reliability of tool-augmented Large Language Models (LLMs). Unlike existing methods that rely solely on semantic similarity …
-
New TRIS defense system combats knowledge poisoning in RAG models
Researchers have developed TRIS, a Tri-Layer Retrieval Integrity Sieve, to combat knowledge poisoning in retrieval-augmented generation (RAG) systems. This middleware defense system sanitizes retrieved evidence by emplo…
-
New DESA method enhances LLM-based retrieval with channel-asymmetric expansion
Researchers have developed DESA (Dense Expansion and Sparse Anchoring), a novel method for improving information retrieval using LLM-based query expansion. Unlike previous approaches that fuse fixed top-L dense and spar…
-
New research explores static pruning and LLM-based query expansion for retrieval systems
Two new research papers explore methods to improve information retrieval systems. The first paper, "Static Pruning Across Sparse Retrieval Regimes," investigates how static pruning techniques can be applied across diffe…
-
New ARGUS system tackles retrieval blind spots in AI models
A new research paper introduces ARGUS, a system designed to identify and fix "blind spots" in retrieval-augmented generation (RAG) models. These blind spots occur when a RAG system fails to retrieve relevant entities du…
-
New ECI method ranks hard-negatives for dense retrieval without training
Researchers have developed a new training-free method called Effective Contrastive Information (ECI) to evaluate hard-negative sources for dense retrieval systems. This technique ranks candidate negatives using frozen e…
-
New benchmark IdioLink tests language models on idiom comprehension
Researchers have introduced IdioLink, a new benchmark designed to evaluate language models' ability to understand idiomatic expressions. The benchmark consists of over 10,000 documents and 2,000 queries, covering 107 id…
-
New RAG methods aim to boost AI factuality and reduce hallucinations
Several research papers published on arXiv in May 2026 introduce novel methods to enhance Retrieval-Augmented Generation (RAG) systems. These approaches focus on improving the robustness and trustworthiness of RAG by ad…